Date Published: October 2019
Comments Due:
Email Questions to:
Planning Note (3/8/2023):
This draft is obsoleted by the initial public draft of NIST AI 100-2, 2023 edition (NIST AI 100-2e2023 ipd).
Author(s)
Elham Tabassi (NIST), Kevin Burns (MITRE), Michael Hadjimichael (MITRE), Andres Molina-Markham (MITRE), Julian Sexton (MITRE)
Announcement
This report is intended as a step toward securing applications of Artificial Intelligence, especially against adversarial manipulations of Machine Learning (ML), by developing a taxonomy and terminology of Adversarial Machine Learning (AML). Although AI also includes various knowledge-based systems, the data-driven approach of ML introduces additional security challenges in training and testing (inference) phases of system operations. AML is concerned with the design of ML algorithms that can resist security challenges, the study of the capabilities of attackers, and the understanding of attack consequences.
This document develops a taxonomy of concepts and defines terminology in the field of AML. The taxonomy, built on and integrating previous AML survey works, is arranged in a conceptual hierarchy that includes key types of attacks, defenses, and consequences. The terminology, arranged in an alphabetical glossary, defines key terms associated with the security of ML components of an AI system. Taken together, the terminology and taxonomy are intended to inform future standards and best practices for assessing and managing the security of ML components, by establishing a common language and understanding of the rapidly developing AML landscape.
NOTE: A call for patent claims is included on page iv of this draft. For additional information, see the Information Technology Laboratory (ITL) Patent Policy--Inclusion of Patents in ITL Publications.
This NIST Interagency/Internal Report (NISTIR) is intended as a step toward securing applications of Artificial Intelligence (AI), especially against adversarial manipulations of Machine Learning (ML), by developing a taxonomy and terminology of Adversarial Machine Learning (AML). Although AI also includes various knowledge-based systems, the data-driven approach of ML introduces additional security challenges in training and testing (inference) phases of system operations. AML is concerned with the design of ML algorithms that can resist security challenges, the study of the capabilities of attackers, and the understanding of attack consequences.
This document develops a taxonomy of concepts and defines terminology in the field of AML. The taxonomy, built on and integrating previous AML survey works, is arranged in a conceptual hierarchy that includes key types of attacks, defenses, and consequences. The terminology, arranged in an alphabetical glossary, defines key terms associated with the security of ML components of an AI system. Taken together, the terminology and taxonomy are intended to inform future standards and best practices for assessing and managing the security of ML components, by establishing a common language and understanding of the rapidly developing AML landscape.
This NIST Interagency/Internal Report (NISTIR) is intended as a step toward securing applications of Artificial Intelligence (AI), especially against adversarial manipulations of Machine Learning (ML), by developing a taxonomy and terminology of Adversarial Machine Learning (AML). Although AI also...
See full abstract
This NIST Interagency/Internal Report (NISTIR) is intended as a step toward securing applications of Artificial Intelligence (AI), especially against adversarial manipulations of Machine Learning (ML), by developing a taxonomy and terminology of Adversarial Machine Learning (AML). Although AI also includes various knowledge-based systems, the data-driven approach of ML introduces additional security challenges in training and testing (inference) phases of system operations. AML is concerned with the design of ML algorithms that can resist security challenges, the study of the capabilities of attackers, and the understanding of attack consequences.
This document develops a taxonomy of concepts and defines terminology in the field of AML. The taxonomy, built on and integrating previous AML survey works, is arranged in a conceptual hierarchy that includes key types of attacks, defenses, and consequences. The terminology, arranged in an alphabetical glossary, defines key terms associated with the security of ML components of an AI system. Taken together, the terminology and taxonomy are intended to inform future standards and best practices for assessing and managing the security of ML components, by establishing a common language and understanding of the rapidly developing AML landscape.
Hide full abstract
Keywords
adversarial; artificial intelligence; attack; cybersecurity; defense; evasion; information technology; machine learning; oracle; poisoning
Control Families
None selected
) or https:// don't prove our archive is authentic, only that you securely accessed it. Note that we are working to fix that :)
